News for hackers. Stuff that matters.

A comment on Scaling Transformer to 1M tokens and beyond with RMT. Parent comment

Re:Scaling Transformer to 1M tokens and beyond with RMT by cubefox on Monday April 24, 2023 @05:43AM (#35685476)
Are there other OpenAI models only available via Azure? I think code-davinci-002, the GPT-3.5 base model, is now only available via Azure. The GPT-4 base model seems to be completely unavailable. The OpenAI playground only has the old GPT-3 base model, davinci.
[ Parent | on HN ]
Re:Scaling Transformer to 1M tokens and beyond with RMT by afro88 on Monday April 24, 2023 @05:25PM (#35693495)
code-davinci-002 is the model used for code completions.

Here's the full list of models: https://learn.microsoft.com/en-us/azure/cognitive-services/o...

[ Parent | on HN ]
Re:Scaling Transformer to 1M tokens and beyond with RMT by cubefox on Tuesday April 25, 2023 @01:05PM (#35703433)
Yeah, it can be also used for that, but the Azure characterization is misleading. The fact is that code-davinci-002 is the GPT-3.5 foundation model, the naked token predictor without any fine-tuning applied to it. See

https://platform.openai.com/docs/model-index-for-researchers

This makes it a very powerful tool in general, since it doesn't suffer from mode collapse. It can be used for anything, though one has to prompt it right, since it doesn't follow instructions by default.

[ Parent | on HN ]